{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:44:21Z","timestamp":1783701861561,"version":"3.55.0"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2015,3,1]],"date-time":"2015-03-01T00:00:00Z","timestamp":1425168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Program for New Century Excellent Talents in Universities","award":["NCET-10-0901"],"award-info":[{"award-number":["NCET-10-0901"]}]},{"name":"National Fundamental Research Program of China","award":["2013CB329401"],"award-info":[{"award-number":["2013CB329401"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2015,3]]},"DOI":"10.1109\/tsmc.2014.2358639","type":"journal-article","created":{"date-parts":[[2014,10,8]],"date-time":"2014-10-08T18:42:54Z","timestamp":1412793774000},"page":"385-398","source":"Crossref","is-referenced-by-count":227,"title":["Multiobjective Reinforcement Learning: A Comprehensive Overview"],"prefix":"10.1109","volume":"45","author":[{"family":"Chunming Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Xin Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Dewen Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNC.2012.6167444"},{"key":"ref38","first-page":"162","article-title":"Reinforcement learning with bounded risk","author":"geibel","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref33","first-page":"746","article-title":"A multi-objective optimization genetic algorithm incorporating preference information","volume":"36","author":"shen","year":"2007","journal-title":"Inf Control"},{"key":"ref32","first-page":"134","article-title":"Action selection methods using reinforcement learning","author":"humphrys","year":"1996","journal-title":"From Animals to Animats 4"},{"key":"ref31","first-page":"1497","article-title":"Managing power consumption and performance of computing systems using reinforcement learning","author":"tesauro","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"2577","article-title":"Self-adaptive multi-objective optimization method design based on agent reinforcement learning for elevator group control systems","author":"zeng","year":"2010","journal-title":"Proc World Congr Int Control Autom"},{"key":"ref37","first-page":"197","article-title":"Multi-criteria reinforcement learning","author":"gabor","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.21.9.967"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/opre.12.4.610"},{"key":"ref34","first-page":"3190","article-title":"Multi-objective reinforcement learning algorithm for MOSDMP in unknown environment","author":"zhao","year":"2010","journal-title":"Proc World Congr Int Control Autom"},{"key":"ref28","article-title":"Learning to solve multiple goals","author":"karlsson","year":"1997"},{"key":"ref27","first-page":"325","article-title":"Reinforcement learning in the operational management of a water system","author":"castelletti","year":"2002","journal-title":"Proc IFAC Workshop on Modeling and Control in Envi Issues"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2106158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50045-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref24","article-title":"Hybrid evolutionary multi-objective optimization with enhanced convergence and diversity","author":"sindhya","year":"2011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEUROPE.2010.5638914"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2055049"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.810758"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2010.10.009"},{"key":"ref25","first-page":"372","article-title":"On the limitations of scalarisation for multi-objective reinforcement learning of Pareto fronts","volume":"5360","author":"vamplew","year":"2008","journal-title":"Proc Australian Joint Conf Artificial Intell"},{"key":"ref50","first-page":"2438","article-title":"Multi-objective reinforcement learning algorithm and its improved convergency method","author":"zhao","year":"2011","journal-title":"Proc IEEE Ind Electron Appl Conf"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11571-008-9066-9"},{"key":"ref59","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref58","first-page":"303","article-title":"Multiobjective optimization using genetic algorithms","volume":"2","author":"zheng","year":"1999","journal-title":"Eng Val Cot Anal"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2007.708"},{"key":"ref56","first-page":"457","article-title":"A fixed-weight RNN dynamic controller for multiple mobile robots","author":"oubbati","year":"2005","journal-title":"Proc IASTED Int Conf Model Ident Control"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368183"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2011.5874921"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.007"},{"key":"ref52","first-page":"396","article-title":"Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning","author":"chen","year":"2010","journal-title":"Proc IEEE Int Conf Autom Logist"},{"key":"ref40","first-page":"325","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"mannor","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref4","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref49","first-page":"274","article-title":"Multi-objective reinforcement learning algorithm and its application in drive system","author":"zhang","year":"2008","journal-title":"Proc 34th Annu IEEE Conf Ind Electron"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007518724497"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2009.92"},{"key":"ref45","first-page":"1","article-title":"Multi-objective optimization by reinforcement learning","author":"liu","year":"2010","journal-title":"Proc IEEE Congr Evol Comput"},{"key":"ref48","first-page":"352","article-title":"Multi-criteria reinforcement learning based on goal-directed exploration and its application to bipedal walking robot","volume":"18","author":"kei","year":"2005","journal-title":"Trans Inst Syst Control Inf Eng"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2007.13.1.69"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390162"},{"key":"ref41","first-page":"1563","article-title":"The steering approach for multi-criteria reinforcement learning","author":"mannor","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252759"},{"key":"ref43","first-page":"1082","article-title":"Balancing multiple sources of reward in reinforcement learning","author":"shelton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-010-9161-0"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2010.5548378"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2010.5611262"},{"key":"ref70","first-page":"530","article-title":"Automated vehicle overtaking based on a multiple-goal reinforcement learning framework","author":"ngai","year":"2010","journal-title":"Proc IEEE Int Conf Control Appl"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s00224-007-9096-4"},{"key":"ref77","first-page":"1902","article-title":"Multiobjective optimization using GAI models","author":"dubus","year":"2009","journal-title":"Proc Int Conf Artif Intell"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-59904-498-9.ch004"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TEVC.2007.892759","article-title":"MOEA\/D: A multiobjective evolutionary algorithm based on decomposition","volume":"11","author":"li","year":"2007","journal-title":"IEEE Trans Evol Comput"},{"key":"ref78","first-page":"490","article-title":"Near admissible algorithms for multiobjective search","author":"perny","year":"2008","journal-title":"Proc Eur Conf Artif Intell"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.4018\/jsir.2011010101"},{"key":"ref60","first-page":"239","article-title":"A POMDP formulation of preference elicitation problems","author":"boutilier","year":"2002","journal-title":"Proc 18th Nat Conf Artif Intell"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref61","first-page":"35","article-title":"Learning an agent’s utility function by observing behavior","author":"chajewska","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102427"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.007"},{"key":"ref65","first-page":"530","article-title":"Multi-objective optimization of freeway traffic flow via a fuzzy reinforcement learning method","volume":"5","author":"yang","year":"2010","journal-title":"Proc 3rd Int Conf Adv Comput Theory Eng"},{"key":"ref66","first-page":"453","article-title":"Efficiency and equity based freeway traffic network flow control","volume":"5","author":"wen","year":"2010","journal-title":"Proc 2nd Int Conf Comput Autom Eng"},{"key":"ref67","first-page":"1","article-title":"Multi-objective reinforcement learning for traffic signal control using vehicular ad hoc network","volume":"2010","author":"duan","year":"2010","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2009.090517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/mind\/LIX.236.433"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ.2003.1209380"},{"key":"ref1","author":"thorndike","year":"1911","journal-title":"Animal Intelligence"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2005.853408"},{"key":"ref94","first-page":"2169","article-title":"Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes","volume":"8","author":"mahadevan","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23938-0_21"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35101-3_53"},{"key":"ref91","first-page":"225","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","author":"devlin","year":"2011","journal-title":"10th Int Conf Auton Agents Multiagent Syst"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2162401"},{"key":"ref90","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc 15th Nat Conf Artif Intell"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2099654"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref99","first-page":"1114","article-title":"A reinforcement learning approach to job-shop scheduling","author":"zhang","year":"1995","journal-title":"Proc 14th Int Joint Conf Artif Intell"},{"key":"ref96","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","article-title":"Efficient reinforcement learning using recursive least-squares methods","volume":"16","author":"xu","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992697"},{"key":"ref11","first-page":"1445","article-title":"Multiple-goal reinforcement learning with modular Sarsa(0)","author":"sprague","year":"2003","journal-title":"Proc 18th Int Joint Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref13","author":"mitsuo","year":"2003","journal-title":"Genetic Algorithms and Engineering Optimization"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-005-0557-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2005.11.018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88910-6"},{"key":"ref82","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"Hierarchical reinforcement learning with the MaxQ value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"J Artif Intell Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-003-0462-y"},{"key":"ref81","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1613\/jair.3987","article-title":"A survey of multi-objective sequential decision-making","volume":"48","author":"roijers","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref84","first-page":"119","article-title":"State abstraction for programmable reinforcement learning agents","author":"andre","year":"2002","journal-title":"Proc 18th Nat Conf Artif Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref83","first-page":"1050","article-title":"Multi-time models for temporally abstract planning","author":"precup","year":"1998","journal-title":"Advances in neural information processing systems"},{"key":"ref80","first-page":"37","article-title":"Hierarchical reinforcement learning for adaptive text generation","author":"dethlefs","year":"2010","journal-title":"Proc 6th Int Natural Lang Gener Conf"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/BICTA.2009.5338123"},{"key":"ref87","doi-asserted-by":"crossref","first-page":"1863","DOI":"10.1109\/TNN.2011.2168422","article-title":"Hierarchial approximate policy iteration with binary-tree state space decomposition","volume":"22","author":"xu","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2010.5461483"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/7031988\/06918520.pdf?arnumber=6918520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:40:59Z","timestamp":1642005659000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6918520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3]]},"references-count":105,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2014.2358639","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3]]}}}